td_algorithm_base

class td_algorithm_base.TDAlgoConfig(n_episodes: int = 0, tolerance: float = 1e-08, render_env: bool = False, render_env_freq: int = - 1, gamma: float = 1.0, alpha: float = 0.1, policy: Optional[Policy] = None, n_itrs_per_episode: int = 100)

Configuration class for TD like algorithms

class td_algorithm_base.TDAlgoBase(algo_config: TDAlgoConfig)

Base class for temporal differences algorithms

__init__(algo_config: TDAlgoConfig)

Constructor. Initialize the agent with the configuration instance needed

Parameters

config (The configuration of the agent) –

actions_after_training_ends(env: Env, **options) → None

Execute any actions the algorithm needs after the iterations are finished

Parameters

• env (The environment to train on) –

• options (Any options passed by the client code) –

Return type

None

actions_before_training_begins(env: Env, **options) → None

Execute any actions the algorithm needs before

Parameters

• env (The environment to train on) –

• options (Any options passed by the client code) –

Return type

None